Keras Deep Learning Cookbook

Getting ready

In this recipe, we develop a modeling pipeline that tries to recognize a digit (0-9) based on images with greater accuracy. The modeling pipelines use CNN models written using the Keras functional API for image classification. 

The Keras library provides a simple method for loading the MNIST data. The dataset is downloaded automatically into the user's home directory as the mnist.pkl.gz (15 MB) file:

from keras.datasets import mnist# get dataset(XTrain, yTrain), (XTest, yTest) = mnist.load_data()

We can see that downloading and loading the MNIST dataset is as easy as calling the mnist.load_data() function:

# plot 4 images as gray scaleplt.subplot(221)plt.imshow(XTrain[1], cmap=plt.get_cmap('gray'))plt.subplot(222)plt.imshow(XTrain[ ...